English(EN) ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models

新的ReaDy方法通过循环状态提高了LLM的草稿速度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员推出了一种新颖的大型语言模型推测解码方法ReaDy，该方法利用混合线性注意力（HLA）模型的循环状态。这种方法通过允许每个草稿位置查询并整合来自模型已提交循环状态的补充上下文来提高草稿效率。在NVIDIA B200 GPU上使用Qwen3.8-27B模型在数学、代码生成和对话基准测试中进行了测试，ReaDy在标准自回归解码方面平均实现了3.16倍的速度提升，在吞吐量和接受长度方面优于现有的DSpark方法。 AI

影响加速LLM推理速度，可能支持更复杂的实时应用并降低计算成本。

排序理由详细介绍LLM推理优化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM推理优化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Bohan Sun, Zunhai Su, Xialie Zhuang, Jianjin Li, Ngai Wong, Chuan-Wei Kuo · 2026-10-15 04:00

ReaDy：循环状态作为混合线性注意力大型语言模型中推测性草稿的动态上下文

arXiv:2610.20503v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden features whose contextual emphasis may not align with the needs of subsequent draft po…

本文如何被排名

报道来源 [1]

ReaDy：循环状态作为混合线性注意力大型语言模型中推测性草稿的动态上下文

相关实体

相关话题